Getting started Community Training Tutorials Documentation APIs, AI & Tools
Teams build AI agents, MCP servers, and APIs across multiple platforms. As a result, it’s challenging to easily reuse, apply consistent security controls, or track end-to-end cost. Agent Fabric is the AI control plane for that landscape. With Agent Fabric, gain visibility across every asset, let agents take action in your existing tech stack, enforce open policies at runtime, and see and optimize what your AI investments are costing.
Sign in to Agent Fabric through the entry point your organization provides, such as Anypoint Platform or a direct URL. The catalogs, dashboards, and governance tools you see depend on the permissions your administrator assigns. To set up access and learn your way around, see Get Started with Agent Fabric.
Watch this video to see how to get started with Agent Fabric:
You can’t apply governance, security, or cost controls to agents you don’t know about. After you capture an inventory of agents, choose the jobs you need those agents to do.
Find every agent, MCP server, and API, and reuse what exists instead of rebuilding assets.
Make the APIs, applications, and agents you already run available as tools, so agents can update records and hand work to other agents without rebuilding the agents.
Put the same authentication, access, and security rules on every agent, MCP server, and LLM call, so production traffic is routed by your rules.
See where token spend goes, cap it, and stop paying frontier models for work smaller models can do.
The registry (Portfolio) is a single inventory of agents, MCP servers, APIs, and related services, regardless of which platform built them. Find what already exists, then keep the catalog current as new assets appear.
Each asset type has its own catalog: Agents, MCP Servers, Model Proxies, APIs (REST and GraphQL), and Gateways (Omni Gateway, external gateways, and unmanaged gateways).
Teams rebuild agents and tools that already exist when they can’t find those assets. Besides your own agents, MCP servers, model proxies, APIs, and gateways, the catalog includes a curated set of public MCP servers from the Official MCP Registry and Informatica.
Find and reuse registered agents, MCP servers, model proxies, APIs, and gateways.
See conformance status and instance health before you use an asset.
Govern, monitor, and manage an asset’s lifecycle from the catalog page.
Publish agents, MCP servers, and APIs so other teams can reuse them.
Use the registry when you start a new agentic project and want to use existing assets or when you want to share assets built by your team.
Learn more: View Your Portfolio
Agents appear on platforms faster than teams can manually register them. Scanners watch supported platforms and automatically register any agents, APIs, and MCP servers they discover to the matching catalog in the registry.
Connect cloud providers as scanner sources in Platform > Providers.
Discover and register agents, MCP servers, and APIs on a schedule or on demand.
See last-run results and how many assets each scan found.
Use scanners when agents run on more than one platform and manual registration can’t keep the registry current.
Learn more: Enable Automated Service Discovery
An agent that can only describe a problem can’t fix it. Agent Fabric exposes your APIs, applications, and agents as tools that those agents can call for help. If needed, Agent Fabric can even coordinate multiple agents when one isn’t enough.
Start by exposing existing APIs as MCP servers, and use an A2A bridge for agents that aren’t A2A-compliant. Add a broker when work spans specialized agents. Use connectors when agents need to call LLMs or other AI services directly.
Your APIs already do the work agents need them to do, but agents can’t call APIs as tools until you expose those APIs as MCP servers. Agent Fabric turns an existing API or SaaS system into an MCP server without custom code and without changing the underlying system.
Publish only the operations agents should call.
Apply existing governance policies to the resulting MCP server.
Expose APIs as MCP servers when agents must call APIs you already have and you don’t want to build a custom MCP server. Create the server from Portfolio > MCP Servers. It appears in the registry automatically.
Learn more: Create MCP Servers with MCP Bridge
MCP Connector uses the Model Context Protocol so AI clients can invoke APIs, connectors, and apps from a Mule application. The resulting MCP server or client runs in Mule. As a server, the app exposes API-led investments, legacy systems, and SaaS applications that don’t natively support MCP. As a client, the app can call external MCP servers.
Expose Mule apps, connectors, and APIs as MCP tools and resources.
Run an MCP server or MCP client inside Mule, without a separate hosting environment.
Use Streamable HTTP (recommended) or SSE (deprecated) for transport.
Use MCP Connector when the tools agents need don’t map to a single existing API and you need custom Mule logic. Build the Mule application in Anypoint Code Builder, and then register the resulting MCP server in Portfolio > MCP Servers. It appears in the registry automatically.
Learn more: MCP Connector
Agent Fabric orchestrates only A2A-compliant agents, but many enterprise agents, including Agentforce agents, aren’t A2A-compliant on their own. An A2A bridge presents those agents as A2A-compliant so they can join your network without being rebuilt.
Make a non-A2A agent A2A-compliant without changing the source agent.
Govern, monitor, and orchestrate the bridged agent like any native A2A agent.
Use A2A Bridge for agents that aren’t yet A2A-compliant. Create the bridge from Portfolio > Agents, and the bridged agent appears in the registry automatically. Use A2A Connector when you need custom Mule application logic.
Learn more: Make an Agent A2A-Compliant
A2A Connector implements the A2A protocol in a Mule application so that application can act as an A2A server, an A2A client, or both.
Add A2A server and client support to a Mule application.
Let agents discover capabilities and delegate specialized tasks to other agents.
Use A2A Connector when existing Mule applications must participate as A2A-compliant agents. Build the application in Anypoint Code Builder.
Learn more: A2A Connector
A broker is an intelligent router that orchestrates work across specialized A2A-compliant agents. It decides which agent handles which task and routes the request to the best-suited agent or broker.
You define the broker and its nodes in Agent Script (.agent files) in an Anypoint Code Builder agent network project. The broker is a graph that mixes deterministic and non-deterministic actions. After you publish an agent network, brokers appear as specialized agents in the registry and can be reused by other brokers.
Include MCP tools and other brokers in the routing graph.
Deploy the agent network, including the broker, to a CloudHub 2.0 shared or private space or to a Runtime Fabric target.
See connections and call volume in Agent Visualizer.
Use a broker when work spans multiple specialized agents.
Learn more: Define Your Agent Network
Agents need the LLMs and knowledge stores you already operate. AI connectors give agentic workflows pre-built access to those models and vector databases so that you don’t need to write a custom integration for each one.
Invoke Agentforce agents and Amazon Bedrock foundation models from Mule.
Call LLMs through the Einstein Trust Layer or through inference APIs from multiple providers.
Use vector stores for search and RAG, and compose LLM, vector, and tool operations in Mule.
Use these connectors when a Mule application must call those AI services directly. Add them to your project in Anypoint Code Builder.
Learn more:
Multi-agent systems are hard to operate when you can’t see how work moves through them. Agent Visualizer maps your agents, MCP servers, and LLMs, including agents from external platforms, to verify routing in development and find bottlenecks and failures in production.
See how agents, brokers, and MCP servers connect.
Watch live request flows and metrics such as latency, throughput, and error rates.
Compare historical patterns when a failure isn’t obvious in real time.
Use Agent Visualizer during development to verify the network, at deployment to confirm routing, and in production to troubleshoot. To see runtime traffic for an agent or MCP server, publish it to Exchange and give it an instance on Omni Gateway.
Learn more: Visualize Agent Networks
Agents that reach production without a defined security, identity, and compliance strategy become a risk, as different platforms enforce different rules, or even none at all. Define that strategy once, and Agent Fabric enforces it on live traffic across every agent, MCP server, and LLM call.
Omni Gateway is Agent Fabric’s runtime enforcement point: a single gateway that sits in front of your agents, APIs, MCP servers, and LLM traffic, regardless of the platform that built them. A managed instance of an API, agent, or MCP server puts Omni Gateway in the request path so policy enforcement applies across data privacy, authentication, compliance, cost controls, and monitoring.
Require authentication and authorization on agent, API, and MCP server requests.
Limit which tools and APIs an agent can call.
Keep an audit trail of traffic for security and compliance.
Set up Omni Gateway in Runtime Manager, and then create managed instances from the Instances tab of an agent, MCP server, or API in Portfolio. Use a managed instance when agents or APIs handle sensitive data, call external systems, or must follow the same runtime rules in every environment. When you don’t need Omni Gateway in the request path, create an unmanaged instance instead. LLM traffic uses a model proxy, which you also deploy to Omni Gateway.
Learn more:
Rewriting the same security, privacy, and cost rules for every agent and service doesn’t scale. A governance strategy defines those rules once and applies them across the agents, APIs, and MCP servers in scope.
Define rules once across access and security, data privacy and integrity, performance and cost, and compliance and observability.
Apply them at the service or instance so live traffic matches the strategy.
Review conformance reports that summarize scores, rule violations, warnings, and severity for each service.
Block or flag noncompliant activity.
Use governance strategies when agents, APIs, and MCP servers must follow the same auditable rules. Create strategies in Governance, and review results on each service’s Conformance Report tab.
Learn more: Work with Governance Strategies
A defined policy isn’t the same as healthy traffic. Monitoring shows latency, error rates, and request volume so that you can catch regressions and decide when to change policy or capacity.
View runtime health metrics for a service.
Compare signals across instances or environments.
Send alerts to Slack, Microsoft Teams, and email.
Use organization-wide dashboards in Observability when your administrator turns them on.
Open a service’s Monitoring tab in Portfolio to use monitoring during development to validate performance and in production to meet SLAs and catch issues before they affect users. For the Mule applications behind your services, use Runtime Manager and Anypoint Monitoring.
Learn more:
On a multi-vendor gateway landscape, the same control is a different native policy on each platform, so gaps appear. Author the intent once with open policies. MuleSoft translates it for each API gateway.
Author a policy once and apply it across gateways from multiple vendors.
Enforce common controls such as API key enforcement, CORS, header manipulation, IP allowlisting, and JWT validation.
Keep the same governance as services move or scale across platforms.
Use open policies when you run gateways from more than one vendor and need the same controls on all of them. Apply them from the Policies tab of a service or instance in Portfolio.
Learn more: Open Policies
Services that run on a third-party API gateway still must meet your standards. Federated governance includes those APIs in the same conformance view so they don’t escape oversight.
Govern third-party APIs alongside MuleSoft-hosted APIs.
Apply, enable, disable, and remove policies on connected Azure API Management, Google Apigee, and Kong Gateway instances from the API instance’s Policies tab in Portfolio, with no Omni Gateway in the request path. Policy write requires a scanner connection whose credentials carry the provider’s write scope.
Monitor conformance across gateways from different vendors.
Use cross-gateway governance when APIs that matter to the business run on a connected third-party gateway and still need to meet your standards.
Learn more:
A compromised, misconfigured, or malicious agent can leak data, take unauthorized actions, or drive unexpected cost. These controls detect that behavior, keep credentials in the vault you already use, and surface known risk on services you’ve already discovered.
Detect and contain rogue agents: Apply Rogue Agent Detection and Agent Kill Switch policies from the Policies tab of each model proxy you want to protect. Detection flags risky behavior for your review. The Kill Switch policy blocks that agent’s access to the model proxy when you quarantine it. Quarantine always requires your review, and you reverse it if needed.
Learn more: Detect and Contain Rogue Agents and Apply and Manage Policies
External vaults: Register an external vault in Platform > Providers so credentials stay in AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault. MuleSoft never stores, displays, or logs secret values. A model proxy can reference a vault secret instead of storing a key.
Learn more: Use Credentials Stored in External Vaults and exp-providers-add.adoc
Akamai risk correlation: Connect Akamai in Platform > Providers to correlate security findings to APIs and MCP services you’ve already discovered, so you can triage risk before it becomes an incident.
Learn more: Correlate Risk Using Akamai API Security and exp-providers-add.adoc
LLM token cost grows without a single place to see it, cap it, or reduce it. Budget management shows that spend and caps it. Cost optimization reduces what each call consumes.
Agents that call each LLM provider directly get a different endpoint, a different policy set, and a different bill. A model proxy, deployed to Omni Gateway, is one governed endpoint for multiple providers. Routing, caching, and policy run in front of every call. Token data from those calls feeds cost management.
Route by model or by meaning (semantic routing).
Reuse similar responses with semantic caching to cut latency and spend.
Apply policies, including the security policies that detect and contain rogue agents.
Use a model proxy when agents call LLMs and you need the same governance, routing, and cost visibility across providers. Create one from Portfolio > Model Proxies on an Omni Gateway running in Connected Mode.
Learn more:
Token usage and spend are visible in one place, so you can track and cap cost. Set model costs so token counts read as dollars. Spend counts only from the time you set those costs. A model wallet identifies a caller of a model proxy, and budgets on the wallet cap that caller’s spend or tokens against a provider.
Monitor organization-wide token usage and spend by provider and by model wallet.
See which budgets are at risk (75% of the limit or more) or at their limit.
Set input and output token costs per model so reports read as dollars.
Add daily, weekly, or monthly budgets to a model wallet, measured by spend or by tokens.
When a wallet reaches its budget, the proxy blocks further requests to that provider’s models, or routes them to the next model if the proxy has a fallback route.
Use budget management when you need visibility and limits on LLM spend. Set model costs in Portfolio > Model Proxies > Models, create model wallets and budgets in Portfolio > Model Proxies > Model Wallets, and track spend in Governance > Cost Management. Model wallets require an identity provider. Budgets are approximate: Usage can briefly exceed a limit before the proxy blocks requests.
Learn more:
A frontier model for a simple task, a repeated prompt, or a bloated payload all add cost without adding value. Optimization policies reduce token consumption for MCP servers, agents, and models without changing what the instance does.
Route by model or by meaning (semantic routing) instead of always using the most expensive model.
Reuse results for similar requests with semantic caching.
Review estimated savings for each model proxy, agent, and MCP server in Governance > Cost Management, then apply the recommended optimization policy, such as MCP Tool Mapping, Clean Payloads, or Semantic Caching.
Use cost optimization when token consumption is a significant cost and you want to reduce spend.
Learn more: Manage Costs and Token Usage
Manage and tune your AI portfolio by registering assets, applying security policies, and monitoring runtime health. Access centralized catalogs to track agents and gateways while verifying compliance through conformance reports and cost management tools. These integrated features help you optimize performance and maintain audit readiness across your environment.
Complete onboarding and access
Confirm your credentials and the permissions your administrator assigned, as described in Agent Fabric Permissions. Finish integration setup for supporting systems, such as connected providers under Platform > Providers. If you plan to use managed instances, A2A bridges, or model proxies, set up an Omni Gateway in Runtime Manager.
Learn the layout
Sign in through your entry path and land on Home. Scan Portfolio catalogs, Governance, Observability, and Platform so you know where to register assets, apply policies, read health signals, and manage providers. For AI assistant usage, see Use the MuleSoft Agent.
Register assets in Portfolio
Under Portfolio, open Agents, MCP Servers, Model Proxies, APIs, or Gateways. Add assets to work with. Register manually or use connected providers under Platform > Providers if your organization enables discovery flows.
Create and manage instances
On Agents, MCP Servers, Model Proxies, and APIs, open Instances to create managed or unmanaged deployments that match your needs. Managed instances run on Omni Gateway and give you stronger governance and monitoring. Gateways and Model Proxies don’t include an Instances tab.
Configure policies
On the Policies tab for a service or instance, apply governance policies that match access control, data privacy, performance, and compliance goals. Use Governance for gateway-wide policy work, organization strategies, and cost tools.
Review compliance
On Agents, APIs, and MCP Servers, open Conformance Report to review scores, violations, and warnings, then address the findings your governance team prioritizes. For gateways, use Governance for the same compliance story at the scope the new experience supports.
Monitor runtime health
On Monitoring, review live metrics such as latency, error rates, and request volume when the new experience surfaces Omni Gateway data for managed paths. Compare what you see with dashboards, reports, or notifications under Observability when your administrator enabled those views for your team. To see how agents, brokers, and MCP servers connect, open Agent Visualizer.
Manage cost
Under Governance, open Cost Management to study token usage and related sUnder Governance, open Cost Management to study token usage and related spend signals. Apply the cost reduction strategies your organization adopted, such as MCP Tool Mapping, Clean Payloads, or Semantic Caching.
Operate and tune the portfolio
Coordinate agents, APIs, gateways, MCP servers, and Model proxies so traffic, policies, and integrations stay aligned. Open Versions when you need configuration history before you change instances or policies. Adjust policies, instances, or registrations when monitoring and governance insights show drift or new risk.
Improve on each cycle
Feed findings from monitoring and governance back into planning for the next change window.
For a guided path through the registry, agent actions, governance, and cost control, get started with the Agent Fabric learning map.
For the technical foundations and capability pillars, explore the Agent Fabric Technical Overview.
For architecture and orchestration design patterns, see the Agent Fabric Deep Dive.